Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- how can you prove that someone is hiding something? if you prove then were they really hiding?by t_minus_40
- Only a matter of time that this research became public.
LLMs were always a great way of exfiltrating targeted data - it’s basically an encrypted malicious payload, and doesn’t “decrypt” until it finds specific inputs
by montyanne - AI models seem like data vacuum cleaners. They crave it more than anything, especially specialized contexts. I wouldn't be surprised if you see hidden goals activate when niche context shows up. Maybe a benchmark asking them to brainstorm in niche fields will lead someone to the trojan horse goals.by dzink
- This has always been my worry with open source models... give them away for free, but with a sleeper agent built in that some arbitrary string can activate. Local deployments will still have web search connectors the majority of the time.by ceroxylon